{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T13:10:09Z","timestamp":1751289009458,"version":"3.41.0"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031965586","type":"print"},{"value":"9783031965593","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-96559-3_2","type":"book-chapter","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T11:55:39Z","timestamp":1751284539000},"page":"21-36","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AlignLLM: Alignment-Based Evaluation Using Ensemble of\u00a0LLMs-as-Judges for\u00a0Q&A"],"prefix":"10.1007","author":[{"given":"Ramitha","family":"Abeyratne","sequence":"first","affiliation":[]},{"given":"Nirmalie","family":"Wiratunga","sequence":"additional","affiliation":[]},{"given":"Kyle","family":"Martin","sequence":"additional","affiliation":[]},{"given":"Ikechukwu","family":"Nkisi-Orji","sequence":"additional","affiliation":[]},{"given":"Lasal","family":"Jayawardena","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,23]]},"reference":[{"key":"2_CR1","unstructured":"Butler, U.: Open Australian legal QA (2023). https:\/\/huggingface.co\/datasets\/umarbutler\/open-australian-legal-qa"},{"key":"2_CR2","unstructured":"Chan, C.M., et al.: ChatEval: towards better LLM-based evaluators through multi-agent debate (2023)"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Chen, B., Zhang, Z., Langren\u00e9, N., Zhu, S.: Unleashing the potential of prompt engineering in large language models: a comprehensive review (2024)","DOI":"10.1016\/j.patter.2025.101260"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Choi, J., Yun, J., Jin, K., Kim, Y.: Multi-News+: cost-efficient dataset cleansing via LLM-based data annotation. In: Al-Onaizan, Y., Bansal, M., Chen, Y.N. (eds.) 2024 EMNLP, pp. 15\u201329. ACL, Miami (2024). https:\/\/aclanthology.org\/2024.emnlp-main.2\/","DOI":"10.18653\/v1\/2024.emnlp-main.2"},{"key":"2_CR5","unstructured":"Craw, S., Massie, S., Wiratunga, N.: Informed case base maintenance: a complexity profiling approach. In: AAAI Conference on Artificial Intelligence (2007). https:\/\/api.semanticscholar.org\/CorpusID:7886047"},{"key":"2_CR6","unstructured":"Dong, Q., et al.: A survey on in-context learning. In: Al-Onaizan, Y., Bansal, M., Chen, Y.N. (eds.) 2024 EMNLP, pp. 1107\u20131128. ACL, Miami (2024). https:\/\/aclanthology.org\/2024.emnlp-main.64\/"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Es, S., James, J., Espinosa\u00a0Anke, L., Schockaert, S.: RAGAs: automated evaluation of retrieval augmented generation. In: Aletras, N., De\u00a0Clercq, O. (eds.) 18th EACL: System Demonstrations, pp. 150\u2013158. ACL, St. Julians (2024). https:\/\/aclanthology.org\/2024.eacl-demo.16\/","DOI":"10.18653\/v1\/2024.eacl-demo.16"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Fei, Y., Hou, Y., Chen, Z., Bosselut, A.: Mitigating label biases for in-context learning. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) 61st ACL (Volume 1: Long Papers), pp. 14014\u201314031. ACL, Toronto (2023). https:\/\/aclanthology.org\/2023.acl-long.783\/","DOI":"10.18653\/v1\/2023.acl-long.783"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Hodson, T., Over, T., Foks, S.: Mean squared error, deconstructed. J. Adv. Model. Earth Syst. 13 (2021)","DOI":"10.1029\/2021MS002681"},{"key":"2_CR10","unstructured":"Kim, S., et al.: Prometheus: inducing fine-grained evaluation capability in language models (2024)"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Lahitani, A.R., Permanasari, A.E., Setiawan, N.A.: Cosine similarity to determine similarity measure: study case in online essay assessment. In: 4th CITSM (2016)","DOI":"10.1109\/CITSM.2016.7577578"},{"key":"2_CR12","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. In: 34th NIPS, NIPS 2020. Curran Associates Inc., Red Hook, NY, USA (2020)"},{"key":"2_CR13","unstructured":"Li, H., et al.: LLMs-as-judges: a comprehensive survey on LLM-based evaluation methods (2024)"},{"key":"2_CR14","unstructured":"Li, R., Patel, T., Du, X.: PRD: peer rank and discussion improve large language model based evaluations. Trans. Mach. Learn. Res. 2024 (2023). https:\/\/api.semanticscholar.org\/CorpusID:259360619"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Liang, S., Zhang, B., Zhao, J., Liu, K.: ABSEval: an agent-based framework for script evaluation. In: Al-Onaizan, Y., Bansal, M., Chen, Y.N. (eds.) 2024 EMNLP, pp. 12418\u201312434. ACL, Miami (2024). https:\/\/aclanthology.org\/2024.emnlp-main.691\/","DOI":"10.18653\/v1\/2024.emnlp-main.691"},{"key":"2_CR16","unstructured":"Lin, C.Y.: ROUGE: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381. ACL, Barcelona (2004)"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Massie, S., Wiratunga, N., Craw, S., Donati, A., Vicari, E.: From anomaly reports to cases, pp. 359\u2013373 (2007)","DOI":"10.1007\/978-3-540-74141-1_25"},{"key":"2_CR18","unstructured":"Naveed, H., et al.: A comprehensive overview of large language models (2023)"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Pan, Q., et al.: Human-centered design recommendations for LLM-as-a-judge. In: Soni, N., Flek, L., Sharma, A., Yang, D., Hooker, S., Schwartz, H.A. (eds.) 1st HuCLLM, pp. 16\u201329. ACL, TBD (2024). https:\/\/aclanthology.org\/2024.hucllm-1.2\/","DOI":"10.18653\/v1\/2024.hucllm-1.2"},{"key":"2_CR20","doi-asserted-by":"publisher","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: BLEU: a method for automatic evaluation of machine translation. In: 40th ACL, ACL 2002, pp. 311\u2013318. ACL, USA (2002). https:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"2_CR21","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1007\/978-3-540-85502-6_30","volume-title":"Advances in Case-Based Reasoning","author":"MA Raghunandan","year":"2008","unstructured":"Raghunandan, M.A., Wiratunga, N., Chakraborti, S., Massie, S., Khemani, D.: Evaluation measures for TCBR systems. In: Althoff, K.D., Bergmann, R., Minor, M., Hanft, A. (eds.) Advances in Case-Based Reasoning, pp. 444\u2013458. Springer, Berlin (2008)"},{"key":"2_CR22","unstructured":"Ru, D., et al.: RAGChecker: a fine-grained framework for diagnosing retrieval-augmented generation (2024)"},{"key":"2_CR23","doi-asserted-by":"publisher","first-page":"e4483","DOI":"10.1136\/bmj.e4483","volume":"345","author":"P Sedgwick","year":"2012","unstructured":"Sedgwick, P.: Pearson\u2019s correlation coefficient. BMJ 345, e4483\u2013e4483 (2012)","journal-title":"BMJ"},{"key":"2_CR24","doi-asserted-by":"publisher","unstructured":"Shankar, S., Zamfirescu-Pereira, J., Hartmann, B., Parameswaran, A., Arawjo, I.: Who validates the validators? Aligning LLM-assisted evaluation of LLM outputs with human preferences. In: 37th ACM UIST, UIST 2024. ACM, New York (2024). https:\/\/doi.org\/10.1145\/3654777.3676450","DOI":"10.1145\/3654777.3676450"},{"key":"2_CR25","unstructured":"Tan, S., et al.: JudgeBench: a benchmark for evaluating LLM-based judges (2024)"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Wiratunga, N., et al.: CBR-RAG: case-based reasoning for retrieval augmented generation in LLMs for legal question answering (2024)","DOI":"10.1007\/978-3-031-63646-2_29"},{"key":"2_CR27","unstructured":"Zhao, R., Zhang, W., Chia, Y.K., Xu, W., Zhao, D., Bing, L.: Auto-arena: automating LLM evaluations with agent peer battles and committee discussions (2024)"},{"key":"2_CR28","unstructured":"Zheng, L., et al.: Judging LLM-as-a-judge with MT-bench and chatbot arena. In: 37th NIPS, NIPS 2023. Curran Associates Inc., Red Hook, NY, USA (2023)"}],"container-title":["Lecture Notes in Computer Science","Case-Based Reasoning Research and Development"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-96559-3_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T12:34:01Z","timestamp":1751286841000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-96559-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031965586","9783031965593"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-96559-3_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"23 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCBR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Case-Based Reasoning","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Biarritz","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccbr2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}